Power market transaction strategy optimization method and system based on data driving

Abstract

The invention relates to the technical field of power system automation, and discloses a power market transaction strategy optimization method and system based on data driving. An inter-provincial electricity market transaction simulation environment containing multiple market members is constructed, a transaction declaration amount boundary is calculated based on a deep reinforcement learning-based transaction declaration auxiliary decision-making model according to the constructed inter-provincial electricity market transaction simulation environment, and model parameters are updated according to a transaction strategy benefit evaluation result. And according to the calculated inter-province power market transaction declaration amount boundary, constructing a corresponding inter-province-intra-province two-level market transaction optimization model, and according to the optimization result, obtaining the transaction declaration amount finally submitted by the target province in the inter-province power market, thereby realizing automatic calculation of the inter-province power market transaction declaration amount, saving human resources, and improving the efficiency. And the operation economy and cleanliness of the power grid of the target province are improved, so that the economic benefits of the target province participating in the inter-province power market are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a data-driven power market transaction strategy optimization method and system. Background Art

[0002] There are abundant new energy (including wind power, photovoltaic, etc.) resources in the northwest of my country, while the power load center is located in the central and eastern regions, and the power supply and demand show a reverse distribution feature. In recent years, the proportion of new energy installed capacity in the Northwest Power Grid has increased rapidly, and it has initially possessed the characteristics of a new power system with a high proportion of new energy electricity. Taking the Gansu Power Grid as an example, as of August 2024, its new energy installed capacity accounted for 62.98%, and its new energy power generation accounted for 37.06% (30.94% after deducting external transmission), ranking second in the country. The power volatility and randomness caused by large-scale new energy access pose a severe challenge to the balance of regional power supply and demand. In order to alleviate the contradiction between the widening gap between power supply and demand and the lack of flexible adjustment resources within the province, it is urgent to achieve the optimal allocation of power resources in a larger range and carry out large-scale inter-provincial and inter-regional power transactions. At present, the Northwest Power Grid has initially established a regional electricity energy market in the Northwest and an auxiliary service trading mechanism covering peak load regulation, standby and other trading products. Considering that the power market reform within the five provinces in the Northwest is also in a gradual deepening process, a unified market and two-level operation of the inter-provincial and intra-provincial two-level power market model will be formed in the future.

[0003] The introduction of the two-tier electricity market model has made the coupling relationship between inter-provincial and intra-provincial electricity transactions closer. Since it will be difficult for most electricity users to directly participate in market declarations for a long time in the future, in the actual operation of the inter-provincial market, most of the transactions are conducted by provincial power companies and their trading centers on behalf of intra-provincial power users. This means that provincial power companies need to use the results of inter-provincial electricity transactions as the boundary conditions for conducting intra-provincial electricity transactions. The results of inter-provincial transactions are bound to have a certain degree of impact on intra-provincial transactions. However, at present, most of the transactions in the inter-provincial electricity market are declared by dispatchers based on their own historical experience. During the period when the power of new energy rises / falls sharply, it is easy to cause misjudgment of power purchase and sales decisions. For example, too little electricity is sold outside, resulting in insufficient power generation space for new energy units in the province and a decrease in the utilization rate of new energy. When the output level of new energy is lower than expected, insufficient repurchased electricity will trigger the guaranteed power purchase mechanism (that is, the regional power grid organizes resources within the region for emergency power support) and cause economic losses.

[0004] To solve the above problems, the present invention proposes a data-driven inter-provincial electricity market transaction strategy optimization method. The method is aimed at intraday transactions in the inter-provincial electricity market. According to the future load power supply demand and new energy consumption demand of the target province's power grid, and taking into account the trading willingness of inter-provincial market members, safety flow transmission restrictions and other factors, the method can automatically calculate the inter-provincial power purchase and sale transaction declaration amount in the next 4 hours (16 time periods). Compared with the existing manual declaration method, it can significantly save human resources and improve economic benefits. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a data-driven electricity market transaction strategy optimization method and system, which can automatically calculate the inter-provincial electricity market transaction declaration volume for intra-day transactions in the inter-provincial electricity market, saving human resources compared to the original manual declaration method. The provided inter-provincial electricity market transaction strategy can take into account the intra-provincial electricity market transaction needs of the target provinces, improve the economy and cleanliness of the target province's power grid operation, and mine historical market transactions, new energy power forecasts and other data based on deep reinforcement learning data-driven technology. It can include new energy / load forecast deviations, market members' trading willingness and other factors into the transaction strategy considerations, thereby further improving the economic benefits of the target provinces participating in the inter-provincial electricity market.

[0006] To achieve the above object, the present invention provides the following technical solutions: In a first aspect of the present invention, a data-driven power market transaction strategy optimization method comprises the following steps: S1: Constructing an inter-provincial power market transaction simulation environment including multiple market members. This step is used to simulate the response strategies of provincial power companies (or other provincial agents) other than the target province (i.e., the provincial power company served by the present invention) to the transaction information reported by the target province, as well as the clearing process of the inter-provincial power market; S2: Using the inter-provincial power market simulation trading environment constructed in S1, the transaction declaration auxiliary decision-making model based on deep reinforcement learning is used to calculate the transaction declaration volume boundary, and the model parameters are updated according to the transaction strategy benefit evaluation results; S3: Based on the transaction declaration volume boundary of the inter-provincial power market calculated in S2, a corresponding inter-provincial and intra-provincial two-level market transaction optimization model is constructed, and the transaction declaration volume finally submitted by the target province in the inter-provincial power market is obtained according to its optimization result.

[0007] Preferably, the S1 includes the following S: S1.1: For provincial power companies (or other provincial agents) other than the target province in the inter-provincial power market, construct their approximate transaction declaration volume function: (1) (2) (3) (4) (5) All the symbols in the above formulas are for provincial power companies. (hereinafter referred to as provinces ) in the period The declaration status is omitted, so the subscript is omitted and In formula (1) and formula (2), and Represents provinces In the period load supply margin and new energy consumption margin. and They respectively represent the upper and lower limits of the total power of all generating units (thermal power, hydropower, energy storage, etc.) except new energy. is the total power upper limit of the new energy units based on the ultra-short-term forecast information. and For the normalized load supply margin and new energy consumption margin, and They respectively represent the normalized basic values ​​corresponding to the load supply margin and the new energy consumption margin. is the shear function, whose purpose is to and is controlled within the range of [0,1]. For Province In the period The transaction reporting volume. Positive value indicates province The opposite means selling electricity. and Represents provinces The minimum demand for power supply margin and new energy consumption margin. The declared transaction volume in formula (5) and , It is a piecewise linear function relationship. The three segments in the function represent three types of situations: purchasing electricity when the power supply margin is insufficient , purchase electricity when there is sufficient margin for new energy consumption And sell electricity when the margin of new energy consumption is insufficient .parameter , and They correspond to the starting values ​​of the three function segments respectively. , and Represent the slopes of the three function segments respectively.

[0013] S1.2: Transaction reporting amount calculated by combining formula (5) , and provinces Historical actual declaration amount , based on the gradient descent algorithm, the unknown parameters in equations (3)-(5) (including , , , , , , and ) to update. Specifically, let all pending parameter sets be ,but It can be expressed as a function . Parameter collection The update method is: (6) (7) in, is the mean square error between the transaction declaration amount calculated by formula (5) and the historical actual declaration amount. is the update step size of the gradient descent method, for right The partial derivative of for Parameters Repeat the calculation of formulas (6) and (5) until Converge to a stable level.

[0016] S1.3: Based on the parameters obtained in S1.2, combined with formula (5), calculate the transaction declaration volume of all market members outside the target province. Combined with the transaction declaration volume of the target province (see S2 for the specific calculation method), perform inter-provincial power market simulation clearing and obtain the transaction volume results. Among them, the quotations of each province continue to use the prices they declared in the day-ahead stage. The inter-provincial power market simulation clearing process refers to the current Northwest Power Grid inter-provincial power market transaction rules. Based on the "high-low matching" method, the purchase and sale transaction pairs with the largest price difference are cleared first, until the transaction volume of the purchaser or seller is zero (when the price difference of multiple transaction pairs is the same, the transaction volume is allocated in proportion to the transaction declaration volume), and the clearing price is the average price of the final cleared purchase and sale transaction pairs.

[0017] Preferably, the S2 includes the following S: S2.1: Initialize the transaction declaration auxiliary decision model. The model consists of three neural networks, including a value network, a strategy network and a historical state memory network. Based on normal probability distribution sampling, the parameters of the value network are randomly generated. , the parameters of the policy network and the parameters of the history state memory network .

[0018] S2.2: Initialize the interactive data pool between the transaction declaration auxiliary decision-making model and the inter-provincial power market transaction simulation environment ,make Is an empty set.

[0019] S2.3: Randomly select any historical period And start calculating. For the period , construct the observed state vector of the transaction declaration decision model . The specific information included is as follows: (8) in, It indicates the predicted value of the total power upper limit of the new energy units corresponding to the next 16 time periods (each time period lasts 15 minutes, and there are 16 time periods in the next 4 hours). It represents the system load power forecast value for the next 16 periods. It represents the total power plan of the tie line in the next 16 periods. It indicates the forecast value of weather forecast information for the next 16 periods. Indicates trading quotes for the next 16 periods. and Respectively represent the previous period Observed traded electricity volume and clearing electricity price. and The previous period Observed forecast deviation of total renewable energy unit power upper limit and system load power forecast deviation. and It was the previous period The observed actual value of the total power of new energy units and the actual value of system load power. In addition to the corresponding data of the target province, and It is also necessary to include shared information of other market members of the inter-provincial power market, which can be obtained through the data acquisition and monitoring control system of the regional power grid. is the historical state memory network in the previous period Output historical status information encoding.

[0021] S2.4: The observation state vector formed by S2.3 The strategy network is input into the transaction declaration auxiliary decision-making model, and the boundary of the inter-provincial power market transaction declaration volume corresponding to the next 16 time periods is generated through this network. .

[0022] S2.5: The inter-provincial power market transaction volume boundary generated by S2.4 As the final transaction declaration amount, it is passed to the inter-provincial power market transaction simulation environment formed by S1, and the inter-provincial power market simulation clearing of S1.3 is executed to obtain the time period Transaction information and clearing price .

[0023] S2.6: Based on the inter-provincial power market clearing results of S2.5, the benefit evaluation of the trading strategy of S3.3 is carried out, which is specifically expressed by the following formula: (9) in, For inter-provincial trading strategies during the period The estimated benefits of , , and The definition of is the same as S1 formula (1)-(5). The first item in the formula represents the cost of electricity purchase and sale, and the second item represents the time period. The penalty for insufficient load supply margin. The third sub-item represents the penalty for insufficient new energy consumption margin. and Represent the weights of the two penalty items respectively.

[0025] S2.7: The observed state vector Input into the historical state memory network and generate historical state information encoding at the same time , forecast value of total power of new energy units and system load power forecast .

[0026] S2.8: Form a data packet based on the results from S2.3 to S2.7 And add it to the interaction data pool Data Pack Specifically include the following information: (10) in, For the corresponding trading period The observed state vector is constructed in the same way as same.

[0028] S2.8.1: Repeat S2.3-2.8 until there are a considerable number of data packets in the experience pool.

[0029] S2.9: Use the data packets in the interactive data pool to update the policy network parameters, value network parameters and auxiliary state memory network parameters of the transaction declaration decision model: (11) (12) (13) in, , , For parameters , , The update step size is , , As parameters, , , The update target is , , For parameters , , The updated gradient of , , They are respectively expressed as follows: (14) (15) (16) in, For parameters Trading strategy before update in session The advantage value of For parameters Transaction reporting volume before and after update The corresponding probability ratio is, is the algorithm parameter that controls the gradient descent amplitude. is the reward function for all data packets in the interactive data pool The cumulative sum of discounts, Declare the output value of the value network in the auxiliary decision model for the transaction.

[0034] S2.10: Repeat S2.2-2.9 until the parameters of various networks in the transaction declaration decision model converge to a stable level.

[0035] Preferably, the S3 includes the following S: S3.1: The time period during which the target provinces need to submit inter-provincial electricity market declarations , construct the power grid observation state vector (The calculation method is the same as S2.3). Input the transaction declaration decision model in S2.10 whose parameters have converged to a stable level to generate the boundary of inter-provincial power market transaction declaration corresponding to the next 16 time periods (The calculation method is the same as S2.4). According to the differences in time periods and transaction objects, It can be further expressed as the following matrix: (17) in Indicates the target province in the time period For provinces The maximum transaction declaration amount, Indicates the target province in the time period For provinces The maximum transaction declaration amount, and so on. is the total number of market members that can trade with the target province.

[0037] S3.2: The mathematical model for optimizing inter-provincial and intra-provincial two-level market transactions in the target province is as follows: (18) (19) (20) (twenty one) (twenty two) Wherein formula (18) is the objective function of the constructed mathematical model, is the objective function of the mathematical model for clearing the electricity market in the target province, Indicates contact line At the moment The amount of inter-provincial electricity market transactions reported, is the target province at time The transaction quotation of . Equations (19)-(23) are the constraints of the constructed mathematical model. Equation (19) is the power limit constraint of the tie line after inter-provincial transactions, It represents the original communication power plan before inter-provincial transactions. represents the interconnection line power plan modified after inter-provincial transactions. Formula (20) is the constraint on the interconnection line power plan adjustment. All provinces A collection of connected contact lines, The target province in S3.1 during the period For provinces The maximum transaction declaration amount. Formula (21) is the power grid safety section flow restriction constraint, It is the time period The corresponding power grid node-safe section power flow transfer factor matrix, Is a node At the moment The node injection power, is the tie line-node correlation factor matrix, and Safety Section At the moment Formula (22) is the power balance constraint of the target province, in which each sub-item includes the power generation power of the units within the province and the power of the interconnection line after the inter-provincial power market transaction. All power generation units (thermal power, hydropower, energy storage, etc.) except new energy are at the same time The total power, Is the new energy unit at all times The total power, is the target province at time The system load power.

[0043] S3.3: Use the mathematical programming solver to solve the two-level market transaction optimization mathematical model constructed in S3.2 to obtain the transaction declaration volume of each interconnection line in the inter-provincial power market. If the inter-provincial power market requires the declaration of transaction volume by interconnection line, the transaction volume declaration It can be submitted directly to the inter-provincial power market; if the inter-provincial power market requires different market members to declare the purchase and sale of electricity, the final transaction declaration amount is calculated as follows: (twenty four) in Indicates the target province in the time period For provinces The final transaction declaration volume.

[0045] If the inter-provincial power market only allows the declaration of the total purchase and sales volume of the province, the final transaction declaration volume is calculated as follows: (25) in Indicates the target province in the time period The final transaction reporting amount.

[0047] Preferably, in S1~3, a simulated trading environment of an inter-provincial electricity market including multiple market members is constructed, a transaction declaration decision-making support model is constructed, and network parameters are updated based on the simulated trading environment of the inter-provincial electricity market; the transaction declaration volume boundary is calculated using the transaction declaration decision-making support model after parameter convergence, and an inter-provincial and intra-provincial two-level market transaction optimization model is constructed based on the transaction declaration volume boundary, and finally the model is solved to obtain the inter-provincial electricity market transaction declaration volume.

[0048] Preferably, the inter-provincial power market simulation transaction environment including multiple market members, the method for constructing the approximate transaction declaration quantity function of the provincial power companies (or provincial agents), and the method for updating the pending parameters in the function.

[0049] Preferably, the transaction declaration decision support model includes an observation state vector construction method for optimizing inter-provincial power market transaction strategies, a model structure including a historical state memory network, a benefit evaluation method for the transaction strategies output by the model, and a parameter update method for the neural network within the model.

[0050] Preferably, the inter-provincial and intra-provincial two-level market transaction optimization model incorporates a constraint condition construction method for the transaction declaration quantity boundary output by the transaction declaration auxiliary decision-making model, as well as a power balance constraint condition construction method that simultaneously considers the power generation capacity of the units within the province and the interconnection line power after the inter-provincial power market transaction.

[0051] In a second aspect of the present invention, a data-driven power market transaction strategy optimization system is implemented, comprising a construction module, an evaluation module and an optimization module; The construction module is used to construct an inter-provincial power market transaction simulation environment including multiple market members, and the construction module is connected to the evaluation module via a network; The evaluation module is used to calculate the transaction declaration volume boundary based on the transaction declaration auxiliary decision model based on deep reinforcement learning according to the constructed inter-provincial power market simulation transaction environment, and the evaluation module is connected to the optimization module through a network; The optimization module is used to calculate the boundary of the inter-provincial power market transaction declaration volume, construct the corresponding inter-provincial and intra-provincial two-level market transaction optimization model, and obtain the transaction declaration volume finally submitted by the target province in the inter-provincial power market according to its optimization results.

[0052] A third aspect of the present invention is a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned data-driven electricity market trading strategy optimization method when executing the computer program.

[0053] A fourth aspect of the present invention is a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data-driven electricity market transaction strategy optimization method are implemented.

[0054] Compared with the prior art, the present invention provides a data-driven power market transaction strategy optimization method and system, which has the following beneficial effects: The invention is based on a data-driven power market transaction strategy optimization method. By constructing an inter-provincial power market transaction simulation environment including multiple market members, the transaction declaration volume boundary is calculated based on the transaction declaration auxiliary decision model based on deep reinforcement learning according to the constructed inter-provincial power market simulation transaction environment, and the model parameters are updated according to the transaction strategy benefit evaluation results. According to the calculated inter-provincial power market transaction declaration volume boundary, a corresponding inter-provincial-intra-provincial two-level market transaction optimization model is constructed. According to the optimization result, the transaction declaration volume finally submitted by the target province in the inter-provincial power market is obtained, and the transaction declaration volume of the inter-provincial power market is automatically calculated, which saves human resources, improves the economic and clean operation of the target province's power grid, and further improves the economic benefits of the target province's participation in the inter-provincial power market. The present invention can automatically calculate the inter-provincial power market transaction declaration volume for the next 4 hours every 15 minutes for intra-day transactions in the inter-provincial power market, saving human resources compared to the original manual declaration method; the inter-provincial power market transaction strategy provided by the present invention can take into account the intra-provincial power market transaction needs of the target province, and improve the economic and clean operation of the power grid in the target province. Specifically, during the period of large-scale power generation of new energy, by increasing the amount of power transmitted to other provinces, the power generation space of new energy units is expanded, and the utilization rate of new energy is improved; during the stage of small-scale power generation of new energy, it is determined whether the load supply margin of the target province is sufficient. If the margin is insufficient, the demand for power purchase is initiated in advance in the inter-provincial power market to avoid the emergency power purchase costs caused by untimely transaction declaration.

[0055] The data-driven technology of deep reinforcement learning in this invention mines data such as historical market transactions and new energy power forecasts, and can incorporate factors such as new energy / load forecast deviations and market members' trading willingness into trading strategy considerations, thereby further improving the economic benefits of target provinces participating in the inter-provincial electricity market. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1This is a flow chart of a data-driven power market transaction strategy optimization method in an embodiment of the present invention.

[0057] Figure 2 This is the statistics of the total power upper limit of new energy in the target province in Example 1 of the present invention.

[0058] Figure 3 This is the system load power statistics of the target province in Example 1 of the present invention.

[0059] Figure 4 This is the transaction declaration and transaction status of the target province participating in the inter-provincial power market in Example 1 of the present invention.

[0060] Figure 5 This is the target province interconnection line power statistics in Example 1 of the present invention.

[0061] Figure 6 Statistics of the total power upper limit and planned power of new energy in the target province in Example 2 of the present invention.

[0062] Figure 7 This is the transaction declaration and transaction status of the target province participating in the inter-provincial power market in Example 2 of the present invention.

[0063] Figure 8 This is the transaction declaration and transaction status of the target province participating in the inter-provincial power market in Example 2 of the present invention.

[0064] Fig. 9 Schematic diagram of the system flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] See also Figure 1-8 , a data-driven power market transaction strategy optimization method, comprising the following steps: S1: Construct an inter-provincial power market transaction simulation environment including multiple market members, where S is used to simulate the response strategies of provincial power companies (or other provincial agents) other than the target province (i.e., the provincial power company served by the present invention) to the transaction information reported by the target province, as well as the clearing process of the inter-provincial power market; S1 includes the following Ss: S1.1: For provincial power companies (or other provincial agents) other than the target province in the inter-provincial power market, construct their approximate transaction declaration volume function: (1) (2) (3) (4) (5) All the symbols in the above formulas are for provincial power companies. (hereinafter referred to as provinces ) in the period The declaration status is omitted, so the subscript is omitted and In formula (1) and formula (2), and Represents provinces In the period load supply margin and new energy consumption margin. and They respectively represent the upper and lower limits of the total power of all generating units (thermal power, hydropower, energy storage, etc.) except new energy. is the total power upper limit of the new energy units based on the ultra-short-term forecast information. and For the normalized load supply margin and new energy consumption margin, and They respectively represent the normalized basic values ​​corresponding to the load supply margin and the new energy consumption margin. is the shear function, whose purpose is to and is controlled within the range of [0,1]. For Province In the period The transaction reporting volume. Positive value indicates province The opposite means selling electricity. and Represents provinces The minimum demand for power supply margin and new energy consumption margin. The declared transaction volume in formula (5) and , It is a piecewise linear function relationship. The three segments in the function represent three types of situations: purchasing electricity when the power supply margin is insufficient , purchase electricity when there is sufficient margin for new energy consumption And sell electricity when the margin of new energy consumption is insufficient .parameter , and They correspond to the starting values ​​of the three function segments respectively. , and Represent the slopes of the three function segments respectively.

[0072] S1.2: Transaction reporting amount calculated by combining formula (5) , and provinces Historical actual declaration amount , based on the gradient descent algorithm, the unknown parameters in equations (3)-(5) (including , , , , , , and ) to update. Specifically, let all pending parameter sets be ,but It can be expressed as a function . Parameter collection The update method is: (6) (7) in, is the mean square error between the transaction declaration amount calculated by formula (5) and the historical actual declaration amount. is the update step size of the gradient descent method, for right The partial derivative of for Parameters Repeat the calculation of formulas (6) and (5) until Converge to a stable level.

[0075] S1.3: Based on the parameters obtained in S1.2, combined with formula (5), calculate the transaction declaration volume of all market members outside the target province. Combined with the transaction declaration volume of the target province (see S2 for the specific calculation method), perform inter-provincial power market simulation clearing and obtain the transaction volume results. Among them, the quotations of each province continue to use the prices they declared in the day-ahead stage. The inter-provincial power market simulation clearing process refers to the current Northwest Power Grid inter-provincial power market transaction rules. Based on the "high-low matching" method, the purchase and sale transaction pairs with the largest price difference are cleared first, until the transaction volume of the power buyer or the power seller is zero (when the price difference of multiple transaction pairs is the same, the transaction volume is allocated in proportion to the transaction declaration volume). The clearing price is the average price of the final cleared purchase and sale transaction pairs. S2: Using the inter-provincial power market simulation trading environment constructed in S1, the transaction declaration auxiliary decision-making model based on deep reinforcement learning is used to calculate the transaction declaration volume boundary, and the model parameters are updated according to the transaction strategy benefit evaluation results; S2 includes the following Ss: S2.1: Initialize the transaction declaration auxiliary decision model. The model consists of three neural networks, including a value network, a strategy network and a historical state memory network. Based on normal probability distribution sampling, the parameters of the value network are randomly generated. , the parameters of the policy network and the parameters of the history state memory network .

[0076] S2.2: Initialize the interactive data pool between the transaction declaration auxiliary decision-making model and the inter-provincial power market transaction simulation environment ,make Is an empty set.

[0077] S2.3: Randomly select any historical period And start calculating. For the period , construct the observed state vector of the transaction declaration decision model . The specific information included is as follows: (8) in, It indicates the predicted value of the total power upper limit of the new energy units corresponding to the next 16 time periods (each time period lasts 15 minutes, and there are 16 time periods in the next 4 hours). It represents the system load power forecast value for the next 16 periods. It represents the total power plan of the tie line in the next 16 periods. It indicates the forecast value of weather forecast information for the next 16 periods. Indicates trading quotes for the next 16 periods. and Respectively represent the previous period Observed traded electricity volume and clearing electricity price. and The previous period Observed forecast deviation of total renewable energy unit power upper limit and system load power forecast deviation. and It was the previous period The observed actual value of the total power of new energy units and the actual value of system load power. In addition to the corresponding data of the target province, and It is also necessary to include shared information of other market members of the inter-provincial power market, which can be obtained through the data acquisition and monitoring control system of the regional power grid. is the historical state memory network in the previous period Output historical status information encoding.

[0079] S2.4: The observation state vector formed by S2.3 The strategy network is input into the transaction declaration auxiliary decision-making model, and the boundary of the inter-provincial power market transaction declaration volume corresponding to the next 16 time periods is generated through this network. .

[0080] S2.5: The inter-provincial power market transaction volume boundary generated by S2.4 As the final transaction declaration amount, it is passed to the inter-provincial power market transaction simulation environment formed by S1, and the inter-provincial power market simulation clearing of S1.3 is executed to obtain the time period Transaction information and clearing price .

[0081] S2.6: Based on the inter-provincial power market clearing results of S2.5, the benefit evaluation of the trading strategy of S3.3 is carried out, which is specifically expressed by the following formula: (9) in, For inter-provincial trading strategies during the period The estimated benefits of , , and The definition of is the same as S1 formula (1)-(5). The first item in the formula represents the cost of electricity purchase and sale, and the second item represents the time period. The penalty for insufficient load supply margin. The third sub-item represents the penalty for insufficient new energy consumption margin. and Represent the weights of the two penalty items respectively.

[0083] S2.7: The observed state vector Input into the historical state memory network and generate historical state information encoding at the same time , forecast value of total power of new energy units and system load power forecast .

[0084] S2.8: Form a data packet based on the results from S2.3 to S2.7 And add it to the interaction data pool Data Pack Specifically include the following information: (10) in, For the corresponding trading period The observed state vector is constructed in the same way as same.

[0086] S2.8.1: Repeat S2.3-2.8 until there are a considerable number of data packets in the experience pool.

[0087] S2.9: Use the data packets in the interactive data pool to update the policy network parameters, value network parameters and auxiliary state memory network parameters of the transaction declaration decision model: (11) (12) (13) in, , , For parameters , , The update step size is , , As parameters, , , The update target is , , For parameters , , The updated gradient of , , They are respectively expressed as follows: (14) (15) (16) in, For parameters Trading strategy before update in session The advantage value of For parameters Transaction reporting volume before and after update The corresponding probability ratio is, is the algorithm parameter that controls the gradient descent amplitude. is the reward function for all data packets in the interactive data pool The cumulative sum of discounts, Declare the output value of the value network in the auxiliary decision model for the transaction.

[0092] S2.10: Repeat S2.2-2.9 until the parameters of various networks in the transaction declaration decision model converge to a stable level; S3: Based on the transaction declaration volume boundary of the inter-provincial power market calculated in S2, a corresponding inter-provincial and intra-provincial two-level market transaction optimization model is constructed, and the transaction declaration volume finally submitted by the target province in the inter-provincial power market is obtained according to the optimization result; S3 includes the following Ss: S3.1: The time period during which the target provinces need to submit inter-provincial electricity market declarations , construct the power grid observation state vector (The calculation method is the same as S2.3). Input the transaction declaration decision model in S2.10 whose parameters have converged to a stable level to generate the boundary of inter-provincial power market transaction declaration volume corresponding to the next 16 time periods (The calculation method is the same as S2.4). According to the differences in time periods and transaction objects, It can be further expressed as the following matrix: (17) in Indicates the target province in the time period For provinces The maximum transaction declaration amount, Indicates the target province in the time period For provinces The maximum transaction declaration amount, and so on. is the total number of market members that can trade with the target province.

[0094] S3.2: The mathematical model for optimizing inter-provincial and intra-provincial two-level market transactions in the target province is as follows: (18) (19) (20) (twenty one) (twenty two) Wherein formula (18) is the objective function of the constructed mathematical model, is the objective function of the mathematical model for clearing the electricity market in the target province, Indicates contact line At the moment The amount of inter-provincial electricity market transactions reported, is the target province at time The transaction quotation of . Equations (19)-(23) are the constraints of the constructed mathematical model. Equation (19) is the power limit constraint of the tie line after inter-provincial transactions, It represents the original communication power plan before inter-provincial transactions. represents the interconnection line power plan modified after inter-provincial transactions. Formula (20) is the constraint on the interconnection line power plan adjustment. All provinces A collection of connected contact lines, The target province in S3.1 during the period For provinces The maximum transaction declaration amount. Formula (21) is the power grid safety section flow restriction constraint, It is the time period The corresponding power grid node-safe section power flow transfer factor matrix, Is a node At the moment The node injection power, is the tie line-node correlation factor matrix, and Safety Section At the moment Formula (22) is the power balance constraint of the target province, in which each sub-item includes the power generation power of the units within the province and the power of the interconnection line after the inter-provincial power market transaction. All power generation units (thermal power, hydropower, energy storage, etc.) except new energy are at the same time The total power, Is the new energy unit at all times The total power, is the target province at time The system load power.

[0100] S3.3: Use the mathematical programming solver to solve the two-level market transaction optimization mathematical model constructed in S3.2 to obtain the transaction declaration volume of each interconnection line in the inter-provincial power market. If the inter-provincial power market requires the declaration of transaction volume by interconnection line, the transaction volume declaration It can be submitted directly to the inter-provincial power market; if the inter-provincial power market requires different market members to declare the purchase and sale of electricity, the final transaction declaration amount is calculated as follows: (twenty four) in Indicates the target province in the time period For provinces The final transaction declaration volume.

[0102] If the inter-provincial power market only allows the declaration of the total purchase and sales volume of the province, the final transaction declaration volume is calculated as follows: (25) in Indicates the target province in the time period The final transaction declaration amount; In S1~3, a simulated trading environment of the inter-provincial power market including multiple market members is constructed, a transaction declaration auxiliary decision model is constructed, and network parameters are updated based on the simulated trading environment of the inter-provincial power market; the transaction declaration auxiliary decision model after parameter convergence is used to calculate the transaction declaration volume boundary, and an inter-provincial and intra-provincial two-level market transaction optimization model is constructed based on the transaction declaration volume boundary, and finally the model is solved to obtain the inter-provincial power market transaction declaration volume; A simulated trading environment of an inter-provincial power market with multiple market members, a method for constructing a function for approximate transaction declaration volume of provincial power companies (or provincial agents), and a method for updating pending parameters in the function; Transaction declaration auxiliary decision model, observation state vector construction method for optimizing inter-provincial power market transaction strategy, model structure including historical state memory network, benefit evaluation method of transaction strategy output by the model, and parameter update method of neural network in the model; The inter-provincial and intra-provincial two-level market transaction optimization model includes the construction method of the constraint conditions of the transaction declaration volume boundary output by the transaction declaration auxiliary decision-making model, and the construction method of the power balance constraint conditions that simultaneously considers the power generation capacity of the intra-provincial units and the power of the interconnection line after the inter-provincial power market transaction; like Fig. 9As shown, in another embodiment of the present invention, a data-driven power market transaction strategy optimization system is provided, including a construction module, an evaluation module and an optimization module; The construction module is used to construct an inter-provincial power market transaction simulation environment including multiple market members, and the construction module is connected to the evaluation module via a network; The evaluation module is used to calculate the transaction declaration volume boundary based on the transaction declaration auxiliary decision model based on deep reinforcement learning according to the constructed inter-provincial power market simulation transaction environment, and the evaluation module is connected to the optimization module through a network; The optimization module is used to calculate the boundary of the inter-provincial power market transaction declaration volume, construct the corresponding inter-provincial and intra-provincial two-level market transaction optimization model, and obtain the transaction declaration volume finally submitted by the target province in the inter-provincial power market according to its optimization results.

[0104] In yet another embodiment of the present invention, a terminal device is provided. The terminal device includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the data-driven power market transaction strategy optimization method, including the following steps: constructing an inter-provincial power market transaction simulation environment including multiple market members; using the constructed inter-provincial power market simulation transaction environment, a transaction declaration auxiliary decision model based on deep reinforcement learning is used to calculate the transaction declaration volume boundary, and at the same time, the model parameters are updated according to the transaction strategy benefit evaluation results; based on the calculated inter-provincial power market transaction declaration volume boundary, a corresponding inter-provincial-intra-provincial two-level market transaction optimization model is constructed, and the transaction declaration volume finally submitted by the target province in the inter-provincial power market is obtained according to its optimization result.

[0105] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory.

[0106] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the data-driven electricity market transaction strategy optimization method in the above-mentioned embodiment; one or more instructions in the computer-readable storage medium are loaded by the processor and execute the following steps: constructing an inter-provincial electricity market transaction simulation environment including multiple market members; using the constructed inter-provincial electricity market simulation transaction environment, a transaction declaration auxiliary decision-making model based on deep reinforcement learning is used to calculate the transaction declaration volume boundary, and at the same time, the model parameters are updated according to the transaction strategy benefit evaluation results; based on the calculated inter-provincial electricity market transaction declaration volume boundary, a corresponding inter-provincial-intra-provincial two-level market transaction optimization model is constructed, and the transaction declaration volume finally submitted by the target province in the inter-provincial electricity market is obtained according to its optimization results.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0112] In order to explain the purpose, technical solutions and advantages of the present invention, the present invention is further described in detail below with reference to the accompanying drawings.

[0113] The Gansu Power Grid in Northwest China is selected as the target province for example analysis, which is divided into the following two examples for discussion: (1) Example 1: Early morning of January 24, 2024 (00:00-08:00) Attached Figure 2The predicted value curve and measured value curve of the total power upper limit of renewable energy corresponding to the early morning period of the target province on that day are shown in the attached figure. Figure 3 The actual system load curve and the predicted system load curve corresponding to the same period are shown. Figure 4 The inter-provincial power market declared volume and actual transaction volume calculated by the present invention for each period are shown in the attached figure. Figure 5 The interconnection line plan (day-ahead interconnection line plan) before the target province participated in the inter-provincial power market, the interconnection line plan (modified plan) after participating in the inter-provincial power market, and the historical actual interconnection line power are displayed. It can be seen that the measured value of the total power of new energy during this period is significantly lower than the predicted value, and the actual value of the system load is significantly higher than the predicted value, so the load power supply margin of the target province is seriously insufficient. Due to inaccurate forecast information, the dispatcher failed to submit a request for inter-provincial power market transactions in a timely manner, and its interconnection line power was negatively biased, that is, the actual interconnection line power was significantly lower than the day-ahead interconnection line plan, and the total deviation power reached 7156 MWh. According to the peak transaction electricity price of the inter-provincial power market (450 yuan / MWh) and the emergency power purchase penalty cost of 20% increase, an additional economic loss of 644,000 yuan will be generated. After the inter-provincial power market transaction is carried out according to the calculation results of the present invention, the deviation power of the actual interconnection line power and the modified plan is reduced to 2106 MWh, and the additional economic loss is reduced to 190,000 yuan, thereby verifying the economic benefits of the present invention in the scenario of insufficient load power supply margin.

[0114] (2) Example 2: Noon on July 11, 2024 (11:00-15:00) Attached Figure 6 The chart shows the predicted and measured curves of the total power upper limit of renewable energy in the target province at noon on the same day, as well as the planned curves of renewable energy units before and after participating in the inter-provincial power market. Figure 7 The inter-provincial power market declared volume and actual transaction volume calculated by the present invention for each period are shown in the attached figure. Figure 8The interconnection line plan (day-ahead interconnection line plan) before the target province participated in the inter-provincial power market, the interconnection line plan (modified plan) after participating in the inter-provincial power market, and the actual interconnection line power are displayed. It can be seen that during this period, due to the insufficient adjustment capacity of flexible resources such as thermal power in the province, the planned curve of the new energy unit is less than its upper limit curve, so the load absorption margin of the target province is insufficient. At this time, the dispatcher did not file an additional power sale request in the inter-provincial power market, and the utilization rate of new energy was low. After the inter-provincial power market transaction was carried out according to the calculation results of the present invention, the modified interconnection line plan was improved from 11:00 to 13:00 compared with the day-ahead interconnection line plan, so the additional planned power generation of new energy units reached 1069 MWh. According to the inter-provincial power market low-end transaction electricity price (150 yuan / MWh), an additional 160,000 yuan of power sales revenue was generated, which verified the economic benefits generated by the present invention in the scenario of insufficient new energy absorption margin.

[0115] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data-driven power market transaction strategy optimization method, characterized in that: The following steps are involved: S1: Construct an inter-provincial electricity market transaction simulation environment involving multiple market members; S2: Using the inter-provincial power market simulation trading environment constructed in S1, the transaction declaration auxiliary decision-making model based on deep reinforcement learning is used to calculate the transaction declaration volume boundary, and the model parameters are updated according to the transaction strategy benefit evaluation results; S3: Based on the transaction declaration volume boundary of the inter-provincial power market calculated in S2, a corresponding inter-provincial and intra-provincial two-level market transaction optimization model is constructed, and the transaction declaration volume finally submitted by the target province in the inter-provincial power market is obtained according to its optimization result.

2. The data-driven power market transaction strategy optimization method according to claim 1 is characterized in that: The S1 includes the following S: S1.1: For provincial power companies other than the target province in the inter-provincial power market, construct their approximate transaction declaration volume function: (1) (2) (3) (4) (5) All the symbols in the above formulas are for provincial power companies. (hereinafter referred to as provinces ) in the period The declaration status is omitted, so the subscript is omitted and ; In formula (1) and formula (2) and Represents provinces In the period The load supply margin and new energy consumption margin; and They represent the upper and lower limits of the total power of all generator sets except renewable energy sources; is the total power upper limit of the new energy units based on the ultra-short-term forecast information; and For the normalized load supply margin and new energy consumption margin, and They represent the normalized basic values ​​corresponding to the load supply margin and the new energy consumption margin respectively; is the shearing function, whose purpose is to and is controlled within the range of [0,1]; For Province In the period The transaction reporting volume; if Positive value indicates province The purchase of electricity, vice versa means selling electricity; and Represents provinces The minimum demand for power supply margin and new energy consumption margin; the declared transaction volume in formula (5) and , It presents a piecewise linear function relationship. The three segments in the function represent three situations: purchasing electricity when the power supply margin is insufficient, purchasing electricity when the new energy consumption margin is sufficient, and selling electricity when the new energy consumption margin is insufficient. The parameters , and They correspond to the starting values ​​of the three function segments respectively. , and Represent the slopes of the three function segments respectively; S1.2: Transaction reporting amount calculated by combining formula (5) , and provinces Historical actual declaration amount , based on the gradient descent algorithm, update the unknown parameters in equations (3)-(5); S1.3: Based on the parameters obtained in S1.2, combined with formula (5), calculate the transaction declaration volume of all market members outside the target province.

3. The data-driven power market transaction strategy optimization method according to claim 2 is characterized in that: The S2 includes the following S: S2.1: Initialize the transaction declaration auxiliary decision model; S2.2: Initialize the interactive data pool between the transaction declaration auxiliary decision-making model and the inter-provincial power market transaction simulation environment ,make is an empty set; S2.3: Randomly select any historical period and start calculating; for the period , construct the observed state vector of the transaction declaration decision model ; S2.4: The observation state vector formed by S2.3 The strategy network is input into the transaction declaration auxiliary decision model, and the boundary of the inter-provincial power market transaction declaration volume corresponding to the future set period is generated through the network. ; S2.5: The inter-provincial power market transaction volume boundary generated by S2.4 As the final transaction declaration amount, it is passed to the inter-provincial power market transaction simulation environment formed by S1, and the inter-provincial power market simulation clearing of S1.3 is executed to obtain the time period Transaction information and clearing price ; S2.6: Based on the inter-provincial electricity market clearing results of S2.5, the benefits of the trading strategy are evaluated, which is specifically expressed by the following formula: (9) in, For inter-provincial trading strategies during the period The estimated benefits of , , and The definition is the same as that of S1 formula (1)-(5); the first sub-item in the formula represents the cost of purchasing and selling electricity, and the second sub-item represents the time period The third sub-item represents the penalty for insufficient margin of load supply and the penalty for insufficient margin of new energy consumption; and Respectively represent the weights of the two penalty items; S2.7: The observed state vector Input into the historical state memory network and generate historical state information encoding at the same time , forecast value of total power of new energy units and system load power forecast ; S2.8: Form a data packet based on the results from S2.3 to S2.7 And add it to the interaction data pool ; Data Packet Specifically include the following information: (10) in, For the corresponding trading period The observed state vector is constructed in the same way as same; S2.9: Use the data packets in the interactive data pool to update the policy network parameters, value network parameters and auxiliary state memory network parameters of the transaction declaration decision model: (11) (12) (13) in, , , For parameters , , The update step size is , , As parameters, , , The update target is , , For parameters , , The updated gradient of , , They are respectively expressed as follows: (14) (15) (16) in, For parameters Trading strategy before update in session The advantage value of For parameters Transaction reporting volume before and after update The corresponding probability ratio is, Algorithm parameters that control the gradient descent amplitude; is the reward function for all data packets in the interactive data pool The cumulative sum of discounts, Declare the output value of the value network in the auxiliary decision model for the transaction; S2.10: Repeat S2.2-2.9 until the parameters of various networks in the transaction declaration decision model converge to a stable level.

4. The data-driven power market transaction strategy optimization method according to claim 3 is characterized by: The S3 includes the following S: S3.1: The time period during which the target provinces need to submit inter-provincial electricity market declarations , construct the power grid observation state vector ; The observed state vector Input the transaction declaration decision model in S2.10 whose parameters have converged to a stable level to generate the boundary of the inter-provincial power market transaction declaration volume corresponding to the future set period ; S3.2: The mathematical model for optimizing inter-provincial and intra-provincial two-level market transactions in the target province is as follows: (18) (19) (20) (21) (22) Wherein formula (18) is the objective function of the constructed mathematical model, is the objective function of the mathematical model for clearing the electricity market in the target province, Indicates contact line At the moment The amount of inter-provincial electricity market transactions reported, is the target province at time The transaction quotation of the inter-provincial transaction is shown in Figure 2. Equations (19)-(23) are the constraints of the constructed mathematical model. Equation (19) is the power limit constraint of the interconnection line after the inter-provincial transaction. It represents the original communication power plan before inter-provincial transactions. represents the interconnection line power plan modified after inter-provincial transactions; Formula (20) is the interconnection line power plan adjustment restriction constraint, All provinces A collection of connected contact lines, The target province in S3.1 during the period For provinces The maximum transaction declaration amount; Formula (21) is the power grid safety section flow restriction constraint, It is the time period The corresponding power grid node-safe section power flow transfer factor matrix, Is a node At the moment The node injection power, is the tie line-node correlation factor matrix, and Safety Section At the moment The lower and upper limits of power flow transmission; Formula (22) is the power balance constraint of the target province, in which each sub-item includes the power generation power of the units within the province and the power of the interconnection line after the inter-provincial power market transaction, All power generation units (thermal power, hydropower, energy storage, etc.) except new energy are at the same time The total power, Is the new energy unit at all times The total power, is the target province at time System load power; S3.3: Use the mathematical programming solver to solve the two-level market transaction optimization mathematical model constructed in S3.2 to obtain the transaction declaration volume of each interconnection line in the inter-provincial power market. .

5. The data-driven power market transaction strategy optimization method according to claim 4 is characterized by: In S1~3, a simulated trading environment of the inter-provincial electricity market including multiple market members is constructed, a transaction declaration decision-making auxiliary model is constructed, and network parameters are updated based on the simulated trading environment of the inter-provincial electricity market; the transaction declaration volume boundary is calculated using the transaction declaration decision-making auxiliary model after parameter convergence, and an inter-provincial and intra-provincial two-level market transaction optimization model is constructed based on the transaction declaration volume boundary, and finally the model is solved to obtain the inter-provincial electricity market transaction declaration volume.

6. The data-driven power market transaction strategy optimization method according to claim 5 is characterized by: The invention discloses a simulated transaction environment of an inter-provincial power market including multiple market members, a method for constructing a function of approximate transaction declaration amount of provincial power companies, and a method for updating pending parameters in the function.

7. The data-driven power market transaction strategy optimization method according to claim 6 is characterized by: The transaction declaration auxiliary decision-making model includes an observation state vector construction method for optimizing inter-provincial power market transaction strategies, a model structure including a historical state memory network, a benefit evaluation method for the transaction strategies output by the model, and a parameter updating method for the neural network in the model.

8. The data-driven power market transaction strategy optimization method according to claim 7 is characterized by: The inter-provincial and intra-provincial two-level market transaction optimization model incorporates a constraint condition construction method for the transaction declaration quantity boundary output by the transaction declaration auxiliary decision-making model, as well as a power balance constraint condition construction method that simultaneously considers the power generation capacity of the intra-provincial units and the interconnection line power after the inter-provincial power market transaction.

9. A data-driven power market transaction strategy optimization system, a data-driven power market transaction strategy optimization method based on rights 1 to 8, characterized in that: The system includes a construction module, an evaluation module, and an optimization module; The construction module is used to construct an inter-provincial power market transaction simulation environment including multiple market members, and the construction module is connected to the evaluation module via a network; The evaluation module is used to calculate the transaction declaration volume boundary based on the transaction declaration auxiliary decision model based on deep reinforcement learning according to the constructed inter-provincial power market simulation transaction environment, and the evaluation module is connected to the optimization module through a network; The optimization module is used to calculate the boundary of the inter-provincial power market transaction declaration volume, construct the corresponding inter-provincial and intra-provincial two-level market transaction optimization model, and obtain the transaction declaration volume finally submitted by the target province in the inter-provincial power market according to its optimization results.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for monitoring wide-band oscillation of a power grid as claimed in any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring wide-band oscillation of a power grid as claimed in any one of claims 1 to 8 are implemented.

Images